no code implementations • 24 Feb 2023 • Erlend Torje Berg Lundby, Adil Rasheed, Ivar Johan Halvorsen, Dirk Reinhardt, Sebastien Gros, Jan Tommy Gravdahl
This simulated dataset can be used in a static deep active learning acquisition scheme referred to as global explorations.
no code implementations • 2 Jan 2023 • Erlend Torje Berg Lundby, Haakon Robinsson, Adil Rasheed, Ivar Johan Halvorsen, Jan Tommy Gravdahl
Neural networks are rapidly gaining interest in nonlinear system identification due to the model's ability to capture complex input-output relations directly from data.
no code implementations • 13 Sep 2022 • Erlend Torje Berg Lundby, Adil Rasheed, Ivar Johan Halvorsen, Jan Tommy Gravdahl
In this work, we demonstrate the value of sparse regularization techniques to significantly reduce the model complexity.